PhotoDNA CSAM Detection System Blog Post

Gemfile

@@ -9,12 +9,15 @@ gem 'rouge'
 
 # If you want to use GitHub Pages, remove the "gem "jekyll"" above and
 # uncomment the line below. To upgrade, run `bundle update github-pages`.
-gem "github-pages", group: :jekyll_plugins
+#gem "github-pages", group: :jekyll_plugins
 
 # If you have any plugins, put them here!
 group :jekyll_plugins do
   gem "jekyll-feed"
+  # Requires JEKYLL_GITHUB_TOKEN
+  gem 'jekyll-github-metadata'
   gem 'jekyll-paginate'
+  gem 'jekyll-seo-tag'
 end
 
 gem 'webrick'

Gemfile.lock

@@ -1,35 +1,17 @@
 GEM
   remote: https://rubygems.org/
   specs:
-    activesupport (6.0.6.1)
-      concurrent-ruby (~> 1.0, >= 1.0.2)
-      i18n (>= 0.7, < 2)
-      minitest (~> 5.1)
-      tzinfo (~> 1.1)
-      zeitwerk (~> 2.2, >= 2.2.2)
     addressable (2.8.8)
       public_suffix (>= 2.0.2, < 8.0)
     base64 (0.3.0)
     bigdecimal (4.0.1)
-    coffee-script (2.4.1)
-      coffee-script-source
-      execjs
-    coffee-script-source (1.12.2)
     colorator (1.1.0)
-    commonmarker (0.23.12)
     concurrent-ruby (1.3.6)
     csv (3.3.5)
-    dnsruby (1.73.1)
-      base64 (>= 0.2)
-      logger (~> 1.6)
-      simpleidn (~> 0.2.1)
     em-websocket (0.5.3)
       eventmachine (>= 0.12.9)
       http_parser.rb (~> 0)
-    ethon (0.15.0)
-      ffi (>= 1.15.0)
     eventmachine (1.2.7)
-    execjs (2.10.0)
     faraday (2.14.0)
       faraday-net_http (>= 2.0, < 3.5)
       json
@@ -38,232 +20,86 @@ GEM
       net-http (~> 0.5)
     ffi (1.17.3-x86_64-linux-gnu)
     forwardable-extended (2.6.0)
-    gemoji (4.1.0)
-    github-pages (232)
-      github-pages-health-check (= 1.18.2)
-      jekyll (= 3.10.0)
-      jekyll-avatar (= 0.8.0)
-      jekyll-coffeescript (= 1.2.2)
-      jekyll-commonmark-ghpages (= 0.5.1)
-      jekyll-default-layout (= 0.1.5)
-      jekyll-feed (= 0.17.0)
-      jekyll-gist (= 1.5.0)
-      jekyll-github-metadata (= 2.16.1)
-      jekyll-include-cache (= 0.2.1)
-      jekyll-mentions (= 1.6.0)
-      jekyll-optional-front-matter (= 0.3.2)
-      jekyll-paginate (= 1.1.0)
-      jekyll-readme-index (= 0.3.0)
-      jekyll-redirect-from (= 0.16.0)
-      jekyll-relative-links (= 0.6.1)
-      jekyll-remote-theme (= 0.4.3)
-      jekyll-sass-converter (= 1.5.2)
-      jekyll-seo-tag (= 2.8.0)
-      jekyll-sitemap (= 1.4.0)
-      jekyll-swiss (= 1.0.0)
-      jekyll-theme-architect (= 0.2.0)
-      jekyll-theme-cayman (= 0.2.0)
-      jekyll-theme-dinky (= 0.2.0)
-      jekyll-theme-hacker (= 0.2.0)
-      jekyll-theme-leap-day (= 0.2.0)
-      jekyll-theme-merlot (= 0.2.0)
-      jekyll-theme-midnight (= 0.2.0)
-      jekyll-theme-minimal (= 0.2.0)
-      jekyll-theme-modernist (= 0.2.0)
-      jekyll-theme-primer (= 0.6.0)
-      jekyll-theme-slate (= 0.2.0)
-      jekyll-theme-tactile (= 0.2.0)
-      jekyll-theme-time-machine (= 0.2.0)
-      jekyll-titles-from-headings (= 0.5.3)
-      jemoji (= 0.13.0)
-      kramdown (= 2.4.0)
-      kramdown-parser-gfm (= 1.1.0)
-      liquid (= 4.0.4)
-      mercenary (~> 0.3)
-      minima (= 2.5.1)
-      nokogiri (>= 1.16.2, < 2.0)
-      rouge (= 3.30.0)
-      terminal-table (~> 1.4)
-      webrick (~> 1.8)
-    github-pages-health-check (1.18.2)
-      addressable (~> 2.3)
-      dnsruby (~> 1.60)
-      octokit (>= 4, < 8)
-      public_suffix (>= 3.0, < 6.0)
-      typhoeus (~> 1.3)
-    html-pipeline (2.14.3)
-      activesupport (>= 2)
-      nokogiri (>= 1.4)
+    google-protobuf (4.33.4)
+      bigdecimal
+      rake (>= 13)
     http_parser.rb (0.8.1)
     i18n (1.14.8)
       concurrent-ruby (~> 1.0)
-    jekyll (3.10.0)
+    jekyll (4.4.1)
       addressable (~> 2.4)
+      base64 (~> 0.2)
       colorator (~> 1.0)
       csv (~> 3.0)
       em-websocket (~> 0.5)
-      i18n (>= 0.7, < 2)
-      jekyll-sass-converter (~> 1.0)
+      i18n (~> 1.0)
+      jekyll-sass-converter (>= 2.0, < 4.0)
       jekyll-watch (~> 2.0)
-      kramdown (>= 1.17, < 3)
+      json (~> 2.6)
+      kramdown (~> 2.3, >= 2.3.1)
+      kramdown-parser-gfm (~> 1.0)
       liquid (~> 4.0)
-      mercenary (~> 0.3.3)
+      mercenary (~> 0.3, >= 0.3.6)
       pathutil (~> 0.9)
-      rouge (>= 1.7, < 4)
+      rouge (>= 3.0, < 5.0)
       safe_yaml (~> 1.0)
-      webrick (>= 1.0)
-    jekyll-avatar (0.8.0)
-      jekyll (>= 3.0, < 5.0)
-    jekyll-coffeescript (1.2.2)
-      coffee-script (~> 2.2)
-      coffee-script-source (~> 1.12)
-    jekyll-commonmark (1.4.0)
-      commonmarker (~> 0.22)
-    jekyll-commonmark-ghpages (0.5.1)
-      commonmarker (>= 0.23.7, < 1.1.0)
-      jekyll (>= 3.9, < 4.0)
-      jekyll-commonmark (~> 1.4.0)
-      rouge (>= 2.0, < 5.0)
-    jekyll-default-layout (0.1.5)
-      jekyll (>= 3.0, < 5.0)
+      terminal-table (>= 1.8, < 4.0)
+      webrick (~> 1.7)
     jekyll-feed (0.17.0)
       jekyll (>= 3.7, < 5.0)
-    jekyll-gist (1.5.0)
-      octokit (~> 4.2)
     jekyll-github-metadata (2.16.1)
       jekyll (>= 3.4, < 5.0)
       octokit (>= 4, < 7, != 4.4.0)
-    jekyll-include-cache (0.2.1)
-      jekyll (>= 3.7, < 5.0)
-    jekyll-mentions (1.6.0)
-      html-pipeline (~> 2.3)
-      jekyll (>= 3.7, < 5.0)
-    jekyll-optional-front-matter (0.3.2)
-      jekyll (>= 3.0, < 5.0)
     jekyll-paginate (1.1.0)
-    jekyll-readme-index (0.3.0)
-      jekyll (>= 3.0, < 5.0)
-    jekyll-redirect-from (0.16.0)
-      jekyll (>= 3.3, < 5.0)
-    jekyll-relative-links (0.6.1)
-      jekyll (>= 3.3, < 5.0)
-    jekyll-remote-theme (0.4.3)
-      addressable (~> 2.0)
-      jekyll (>= 3.5, < 5.0)
-      jekyll-sass-converter (>= 1.0, <= 3.0.0, != 2.0.0)
-      rubyzip (>= 1.3.0, < 3.0)
-    jekyll-sass-converter (1.5.2)
-      sass (~> 3.4)
+    jekyll-sass-converter (3.1.0)
+      sass-embedded (~> 1.75)
     jekyll-seo-tag (2.8.0)
       jekyll (>= 3.8, < 5.0)
-    jekyll-sitemap (1.4.0)
-      jekyll (>= 3.7, < 5.0)
-    jekyll-swiss (1.0.0)
-    jekyll-theme-architect (0.2.0)
-      jekyll (> 3.5, < 5.0)
-      jekyll-seo-tag (~> 2.0)
-    jekyll-theme-cayman (0.2.0)
-      jekyll (> 3.5, < 5.0)
-      jekyll-seo-tag (~> 2.0)
-    jekyll-theme-dinky (0.2.0)
-      jekyll (> 3.5, < 5.0)
-      jekyll-seo-tag (~> 2.0)
-    jekyll-theme-hacker (0.2.0)
-      jekyll (> 3.5, < 5.0)
-      jekyll-seo-tag (~> 2.0)
-    jekyll-theme-leap-day (0.2.0)
-      jekyll (> 3.5, < 5.0)
-      jekyll-seo-tag (~> 2.0)
-    jekyll-theme-merlot (0.2.0)
-      jekyll (> 3.5, < 5.0)
-      jekyll-seo-tag (~> 2.0)
-    jekyll-theme-midnight (0.2.0)
-      jekyll (> 3.5, < 5.0)
-      jekyll-seo-tag (~> 2.0)
-    jekyll-theme-minimal (0.2.0)
-      jekyll (> 3.5, < 5.0)
-      jekyll-seo-tag (~> 2.0)
-    jekyll-theme-modernist (0.2.0)
-      jekyll (> 3.5, < 5.0)
-      jekyll-seo-tag (~> 2.0)
-    jekyll-theme-primer (0.6.0)
-      jekyll (> 3.5, < 5.0)
-      jekyll-github-metadata (~> 2.9)
-      jekyll-seo-tag (~> 2.0)
-    jekyll-theme-slate (0.2.0)
-      jekyll (> 3.5, < 5.0)
-      jekyll-seo-tag (~> 2.0)
-    jekyll-theme-tactile (0.2.0)
-      jekyll (> 3.5, < 5.0)
-      jekyll-seo-tag (~> 2.0)
-    jekyll-theme-time-machine (0.2.0)
-      jekyll (> 3.5, < 5.0)
-      jekyll-seo-tag (~> 2.0)
-    jekyll-titles-from-headings (0.5.3)
-      jekyll (>= 3.3, < 5.0)
     jekyll-watch (2.2.1)
       listen (~> 3.0)
-    jemoji (0.13.0)
-      gemoji (>= 3, < 5)
-      html-pipeline (~> 2.2)
-      jekyll (>= 3.0, < 5.0)
     json (2.18.0)
-    kramdown (2.4.0)
-      rexml
+    kramdown (2.5.1)
+      rexml (>= 3.3.9)
     kramdown-parser-gfm (1.1.0)
       kramdown (~> 2.0)
     liquid (4.0.4)
-    listen (3.9.0)
+    listen (3.10.0)
+      logger
       rb-fsevent (~> 0.10, >= 0.10.3)
       rb-inotify (~> 0.9, >= 0.9.10)
     logger (1.7.0)
-    mercenary (0.3.6)
-    minima (2.5.1)
-      jekyll (>= 3.5, < 5.0)
-      jekyll-feed (~> 0.9)
-      jekyll-seo-tag (~> 2.1)
-    minitest (5.27.0)
+    mercenary (0.4.0)
     net-http (0.9.1)
       uri (>= 0.11.1)
-    nokogiri (1.19.0-x86_64-linux-gnu)
-      racc (~> 1.4)
-    octokit (4.25.1)
+    octokit (6.1.1)
       faraday (>= 1, < 3)
       sawyer (~> 0.9)
     pathutil (0.16.2)
       forwardable-extended (~> 2.6)
-    public_suffix (5.1.1)
-    racc (1.8.1)
+    public_suffix (7.0.2)
+    rake (13.3.1)
     rb-fsevent (0.11.2)
     rb-inotify (0.11.1)
       ffi (~> 1.0)
     rexml (3.4.4)
-    rouge (3.30.0)
-    rubyzip (2.4.1)
+    rouge (4.7.0)
     safe_yaml (1.0.5)
-    sass (3.7.4)
-      sass-listen (~> 4.0.0)
-    sass-listen (4.0.0)
-      rb-fsevent (~> 0.9, >= 0.9.4)
-      rb-inotify (~> 0.9, >= 0.9.7)
+    sass-embedded (1.97.2-x86_64-linux-gnu)
+      google-protobuf (~> 4.31)
     sawyer (0.9.3)
       addressable (>= 2.3.5)
       faraday (>= 0.17.3, < 3)
-    simpleidn (0.2.3)
-    terminal-table (1.8.0)
-      unicode-display_width (~> 1.1, >= 1.1.1)
+    terminal-table (3.0.2)
+      unicode-display_width (>= 1.1.1, < 3)
     thread_safe (0.3.6)
-    typhoeus (1.5.0)
-      ethon (>= 0.9.0, < 0.16.0)
     tzinfo (1.2.11)
       thread_safe (~> 0.1)
-    tzinfo-data (1.2022.1)
+    tzinfo-data (1.2025.3)
       tzinfo (>= 1.0.0)
-    unicode-display_width (1.8.0)
+    unicode-display_width (2.6.0)
     uri (1.1.1)
     wdm (0.1.1)
-    webrick (1.8.2)
-    zeitwerk (2.7.4)
+    webrick (1.9.2)
 
 PLATFORMS
   x86_64-linux
@@ -272,9 +108,10 @@ DEPENDENCIES
   base64
   bigdecimal
   csv
-  github-pages
   jekyll-feed
+  jekyll-github-metadata
   jekyll-paginate
+  jekyll-seo-tag
   kramdown
   rouge
   tzinfo (~> 1.2)
@@ -283,4 +120,4 @@ DEPENDENCIES
   webrick
 
 BUNDLED WITH
-   2.3.8
+  4.0.3

_category/ml-data-engineering.md

@@ -0,0 +1,4 @@
+---
+team: ML Data Engineering
+permalink: "/blog/category/ml-data-engineering"
+---

_data/authors.yml

@@ -177,3 +177,9 @@ moniquec:
   github: MAlvesCruz
   about: |
     Monique is a data scientist on the Applied Research team building machine learning models to understand and connect our content.
+
+anishk123:
+  name: Anish Kumar
+  github: anishk123
+  about: |
+    Anish is an engineer on the Machine Learning Data Engineering team building LLM workflows and data pipelines to enrich our content and improve our trust and safety systems.